Partial-Node-Based State Estimation for Delayed Complex Networks Under Intermittent Measurement Outliers: A Multiple-Order-Holder Approach

• Published in: IEEE transaction on neural networks and learning systems Vol. 34; no. 10; pp. 7181 - 7195
• Main Authors: Zou, Lei, Wang, Zidong, Hu, Jun, Dong, Hongli
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.10.2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Complex networks; Delayed complex networks (DCNs); Electronic mail; intermittent measurement outliers (IMOs); multi-order-holder; Noise (mathematics); Optimization; Outliers (statistics); partial-node-based (PNB) state estimation; Resists; Sequences; State estimation; Technological innovation; Time measurement; ultimate boundedness; Weight measurement
• ISSN: 2162-237X; 2162-2388; 2162-2388
• DOI: 10.1109/TNNLS.2021.3138979

This article is concerned with the partial-node-based (PNB) state estimation problem for delayed complex networks (DCNs) subject to intermittent measurement outliers (IMOs). In order to describe the intermittent nature of outliers, several sequences of shifted gate functions are adopted to model the occurrence moments and the disappearing moments of IMOs. Two outlier-related indices, namely, minimum and maximum interval lengths, are employed to parameterize the "occurrence frequency" of IMOs. The norm of the addressed outlier is allowed to be greater than a certain fixed threshold, and this distinguishes the outlier from the extensively studied norm-bounded noise. By adopting the input-output models of the considered complex network, a novel multiple-order-holder (MOH) approach is developed to resist the effects of IMOs by dedicatedly designing a weighted average of certain non-IMO measurements, and then, a PNB state estimator is constructed based on the outputs of the MOHs. Sufficient conditions are proposed to ensure the exponentially ultimate boundedness (EUB) of the resultant estimation error, and the estimator gain matrices are subsequently obtained by solving a constrained optimization problem. Finally, two simulation examples are provided to demonstrate the effectiveness of our developed outlier-resistant PNB state estimation scheme.